Diffhash: Text-guided Targeted Attack Via Diffusion Models Against Deep Hashing Image Retrieval

Abstract

Deep hashing models have been widely adopted to tackle the challenges of large-scale image retrieval. However, these approaches face serious security risks due to their vulnerability to adversarial examples. Despite the increasing exploration of targeted attacks on deep hashing models, existing approaches still suffer from a lack of multimodal guidance, reliance on labeling information and dependence on pixel-level operations for attacks. To address these limitations, we proposed DiffHash, a novel diffusion-based targeted attack for deep hashing. Unlike traditional pixel-based attacks that directly modify specific pixels and lack multimodal guidance, our approach focuses on optimizing the latent representations of images, guided by text information generated by a Large Language Model (LLM) for the target image. Furthermore, we designed a multi-space hash alignment network to align the high-dimension image space and text space to the low-dimension binary hash space. During reconstructio

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2025diffhash

Related papers

• Targeted Attack For Deep Hashing Based Retrieval (2020)13.65
• Darkhash: A Data-free Backdoor Attack Against Deep Hashing (2025)2.26
• Model Inversion Attack Against Deep Hashing (2025)0.00
• Badhash: Invisible Backdoor Attacks Against Deep Hashing With Clean Label (2022)11.19
• Clean Image May Be Dangerous: Data Poisoning Attacks Against Deep Hashing (2025)0.00
• Semantic-aware Adversarial Training For Reliable Deep Hashing Retrieval (2023)13.49
• Unsupervised Multi-criteria Adversarial Detection In Deep Image Retrieval (2023)0.00
• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35